Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Paolo Bonzini:
 "On the x86 side, there are some optimizations and documentation
  updates.  The big ARM/KVM change for 3.11, support for AArch64, will
  come through Catalin Marinas's tree.  s390 and PPC have misc cleanups
  and bugfixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (87 commits)
  KVM: PPC: Ignore PIR writes
  KVM: PPC: Book3S PR: Invalidate SLB entries properly
  KVM: PPC: Book3S PR: Allow guest to use 1TB segments
  KVM: PPC: Book3S PR: Don't keep scanning HPTEG after we find a match
  KVM: PPC: Book3S PR: Fix invalidation of SLB entry 0 on guest entry
  KVM: PPC: Book3S PR: Fix proto-VSID calculations
  KVM: PPC: Guard doorbell exception with CONFIG_PPC_DOORBELL
  KVM: Fix RTC interrupt coalescing tracking
  kvm: Add a tracepoint write_tsc_offset
  KVM: MMU: Inform users of mmio generation wraparound
  KVM: MMU: document fast invalidate all mmio sptes
  KVM: MMU: document fast invalidate all pages
  KVM: MMU: document fast page fault
  KVM: MMU: document mmio page fault
  KVM: MMU: document write_flooding_count
  KVM: MMU: document clear_spte_count
  KVM: MMU: drop kvm_mmu_zap_mmio_sptes
  KVM: MMU: init kvm generation close to mmio wrap-around value
  KVM: MMU: add tracepoint for check_mmio_spte
  KVM: MMU: fast invalidate all mmio sptes
  ...

1 files changed, 60 insertions, 20 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 292e6ca89f42..d21bce505315 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1193,20 +1193,37 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
+		int faulted = 0;
+
 		/* n.b - signed multiplication and division required */
 		usdiff = data - kvm->arch.last_tsc_write;
 #ifdef CONFIG_X86_64
 		usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
 #else
 		/* do_div() only does unsigned */
-		asm("idivl %2; xor %%edx, %%edx"
-		: "=A"(usdiff)
-		: "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
+		asm("1: idivl %[divisor]\n"
+		    "2: xor %%edx, %%edx\n"
+		    "   movl $0, %[faulted]\n"
+		    "3:\n"
+		    ".section .fixup,\"ax\"\n"
+		    "4: movl $1, %[faulted]\n"
+		    "   jmp  3b\n"
+		    ".previous\n"
+
+		_ASM_EXTABLE(1b, 4b)
+
+		: "=A"(usdiff), [faulted] "=r" (faulted)
+		: "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz));
+
 #endif
 		do_div(elapsed, 1000);
 		usdiff -= elapsed;
 		if (usdiff < 0)
 			usdiff = -usdiff;
+
+		/* idivl overflow => difference is larger than USEC_PER_SEC */
+		if (faulted)
+			usdiff = USEC_PER_SEC;
 	} else
 		usdiff = USEC_PER_SEC; /* disable TSC match window below */
 
@@ -1587,6 +1604,30 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	return 0;
 }
 
+/*
+ * kvmclock updates which are isolated to a given vcpu, such as
+ * vcpu->cpu migration, should not allow system_timestamp from
+ * the rest of the vcpus to remain static. Otherwise ntp frequency
+ * correction applies to one vcpu's system_timestamp but not
+ * the others.
+ *
+ * So in those cases, request a kvmclock update for all vcpus.
+ * The worst case for a remote vcpu to update its kvmclock
+ * is then bounded by maximum nohz sleep latency.
+ */
+
+static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+{
+	int i;
+	struct kvm *kvm = v->kvm;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+		kvm_vcpu_kick(vcpu);
+	}
+}
+
 static bool msr_mtrr_valid(unsigned msr)
 {
 	switch (msr) {
@@ -1984,7 +2025,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		kvmclock_reset(vcpu);
 
 		vcpu->arch.time = data;
-		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+		kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
 		/* we verify if the enable bit is set... */
 		if (!(data & 1))
@@ -2701,7 +2742,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		 * kvmclock on vcpu->cpu migration
 		 */
 		if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1)
-			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+			kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 		if (vcpu->cpu != cpu)
 			kvm_migrate_timers(vcpu);
 		vcpu->cpu = cpu;
@@ -5238,7 +5279,13 @@ static void kvm_set_mmio_spte_mask(void)
 	 * Set the reserved bits and the present bit of an paging-structure
 	 * entry to generate page fault with PFER.RSV = 1.
 	 */
-	mask = ((1ull << (62 - maxphyaddr + 1)) - 1) << maxphyaddr;
+	 /* Mask the reserved physical address bits. */
+	mask = ((1ull << (51 - maxphyaddr + 1)) - 1) << maxphyaddr;
+
+	/* Bit 62 is always reserved for 32bit host. */
+	mask |= 0x3ull << 62;
+
+	/* Set the present bit. */
 	mask |= 1ull;
 
 #ifdef CONFIG_X86_64
@@ -5498,13 +5545,6 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
 	char instruction[3];
 	unsigned long rip = kvm_rip_read(vcpu);
 
-	/*
-	 * Blow out the MMU to ensure that no other VCPU has an active mapping
-	 * to ensure that the updated hypercall appears atomically across all
-	 * VCPUs.
-	 */
-	kvm_mmu_zap_all(vcpu->kvm);
-
 	kvm_x86_ops->patch_hypercall(vcpu, instruction);
 
 	return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
@@ -5702,6 +5742,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			__kvm_migrate_timers(vcpu);
 		if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu))
 			kvm_gen_update_masterclock(vcpu->kvm);
+		if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu))
+			kvm_gen_kvmclock_update(vcpu);
 		if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) {
 			r = kvm_guest_time_update(vcpu);
 			if (unlikely(r))
@@ -6812,6 +6854,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		return -EINVAL;
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
+	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
@@ -7040,22 +7083,18 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	 * If memory slot is created, or moved, we need to clear all
 	 * mmio sptes.
 	 */
-	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
-		kvm_mmu_zap_mmio_sptes(kvm);
-		kvm_reload_remote_mmus(kvm);
-	}
+	kvm_mmu_invalidate_mmio_sptes(kvm);
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
-	kvm_mmu_zap_all(kvm);
-	kvm_reload_remote_mmus(kvm);
+	kvm_mmu_invalidate_zap_all_pages(kvm);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
-	kvm_arch_flush_shadow_all(kvm);
+	kvm_mmu_invalidate_zap_all_pages(kvm);
 }
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
@@ -7263,3 +7302,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);